- GEN AI SECURITY
- Initiatives
OWASP Top 10 for LLM and GenAI
The OWASP Top 10 for LLM and GenAI Initiative is a global, community-driven effort focused on identifying, documenting, and raising awareness of the most critical security risks impacting Large Language Models (LLMs), Generative AI (GenAI), and emerging Agentic AI systems. Originally established as the OWASP Top 10 for Large Language Model Applications, the initiative has […]
- Github
- Initiative Charter
What’s New
大規模言語モデル（LLM）アプリケーションに関するOWASP Top 10
大規模言語モデル（LLM）アプリケーションに関するOWASP Top 10は、AIアプリケーション特有のセキュリティ問題を浮き彫りにし、対処するためのコミュニティ主導の取り組みとして2023年に開始されました。それ以来、この技術はさまざまな業界やアプリケーションに広がり続け、それに伴うリスクも増大しています。LLMが顧客とのやり取りから社内業務に至るまで、あらゆるものに深く組み込まれるにつれて、開発者やセキュリティ専門家は新たな脆弱性を発見し、その対策案に貢献しています。
2025 में LLM Applications के लि ए OWASP के शी र्ष 10
बड़े भाषा मॉडल अनुप्रयोगों के लिए OWASP शीर्ष 10 2023 में AI अनुप्रयोगों के लिए विशिष्ट सुरक्षा मुद्दों को उजागर करने और संबोधित करने के लिए
OWASP Τοπ-10 για Εφαρμογές LLM 2025
Το OWASP Τοπ-10 για Εφαρμογές Μεγάλων Γλωσσικών Μοντέλων (LLM) ξεκίνησε το 2023 ως πρωτοβουλία της κοινότητας με στόχο να επισημάνει και να αντιμετωπίσει ζητήματα ασφάλειας ειδικά
LLM 애플리케이션을 위한 OWASP Top 10 2025
LLM 애플리케이션을 위한 OWASP Top 10은 2023년 AI 애플리케이션 관련 보안 문제를 해결하기 위한 커뮤니티 주도의 노력으로 시작되었습니다. 그로부터 이 기술은 산업과 애플리케이션 전반에 걸쳐 계속
OWASP Top 10 для LLM и генеративного ИИ (2025)
Это обновление — актуальный и всеобъемлющий ресурс, который охватывает ключевые риски, уязвимости и методы их устранения для защиты генеративного ИИ и LLM-приложений на всех этапах их
OWASP Top 10 para Aplicações de LLM e IA Generativa (2025)
Esta atualização oferece um recurso abrangente e atualizado que aborda os principais riscos, vulnerabilidades e medidas de proteção para garantir a segurança das aplicações de IA
Initiative Meetings
Monday
- 2:30 PM (EST)
Top 10 Weekly Meeting
- One Time
- Outlook
Day of the Week
Tuesdays
2:30 PM (EST)
Related Workstreams & Slack Channels
| Initiative Workstream | Initiative Workstream Slack Channel |
|---|---|
| prompt-injection | #team-genai-top-10-llm-llm01-prompt-injection |
| sensitive-information-disclosure | #team-genai-top-10-llm-llm02-sensitive-information-disclosure |
| supply-chain-vulnerabilities | #team-genai-top-10-llm-llm03-supply-chain-vulnerabilities |
| data-and-model-poisoning | #team-genai-top-10-llm-llm04-data-and-model-poisoning |
| improper-output-handling | #team-genai-top-10-llm-llm05-improper-output-handling |
| excessive-agency | #team-genai-top-10-llm-llm06-excessive-agency |
| system-prompt-leakage | #team-genai-top-10-llm-llm07-system-prompt-leakage |
| vector-and-embedding-weaknesses | #team-genai-top-10-llm-llm08-vector-and-embedding-weaknesses |
| misinformation | #team-genai-top-10-llm-llm09-misinformation |
| unbounded-consumption | #team-genai-top-10-llm-llm10-unbounded-consumption |
Workstream Leads
| Initiative Workstream Lead | Initiative Workstream Name | Initiative Workstream Lead Linkedin |
|---|---|---|
| Hyrum Anderson | https://www.linkedin.com/in/hyrumanderson/ | |
| Pete Bryan | https://www.linkedin.com/in/pete-bryan-77588473/ | |
| Michael Bargury | https://www.linkedin.com/in/michaelbargury/ | |
| Daniel Jones | https://www.linkedin.com/in/daniel-jones-429418ba/ | |
| Mavro udivo | https://www.linkedin.com/in/mavroudisv/ | |
| Egor Pushkin | https://www.linkedin.com/in/egorpushkin/ | |
| Axsa Ucedo | https://www.linkedin.com/in/axsaucedo/ |
Initiative Community Awards - Agentic Security Hall of Fame
| Initiative Awards Name | Initiative Awards Companyaffiliation | Initiative Awards Profile Link | Initiative Awards Award |
|---|---|---|---|
| Harrison Muchnic | Pomu-io | https://www.linkedin.com/in/harrisonmuchnic/ | NY Agentic Hackathon Winner |
| Arjun Ramakrishnan | Mastercard | https://www.linkedin.com/in/arjun-ramakrishnan-cybersec/ | NY Agentic Hackathon Winner |
| Perly Dahan | Universal Music Group | https://www.linkedin.com/in/perla-dahan/ | NY Agentic Hackathon Winner |